Paper · arXiv 2309.03185
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
Lily Goli, Cody Reading, Silvia Selllán, Alec Jacobson, Andrea Tagliasacchi
BayesRays is a post-hoc framework that evaluates uncertainty in pre-trained NeRFs using spatial perturbations and Bayesian Laplace approximation, improving key metrics and applications.
Abstract
Neural Radiance Fields (NeRFs) have shown promise in applications like view synthesis and depth estimation, but learning from multiview images faces inherent uncertainties. Current methods to quantify them are either heuristic or computationally demanding. We introduce BayesRays, a post-hoc framework to evaluate uncertainty in any pre-trained NeRF without modifying the training process. Our method establishes a volumetric uncertainty field using spatial perturbations and a Bayesian Laplace approximation. We derive our algorithm statistically and show its superior performance in key metrics and applications. Additional results available at: https://bayesrays.github.io.